Skip to main content

Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding

  • Conference paper
  • First Online:
Computer Vision – ECCV 2024 (ECCV 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15134))

Included in the following conference series:

  • 279 Accesses

Abstract

3D visual grounding is the task of localizing the object in a 3D scene which is referred by a description in natural language. With a wide range of applications ranging from autonomous indoor robotics to AR/VR, the task has recently risen in popularity. A common formulation to tackle 3D visual grounding is grounding-by-detection, where localization is done via bounding boxes. However, for real-life applications that require physical interactions, a bounding box insufficiently describes the geometry of an object. We therefore tackle the problem of dense 3D visual grounding, i.e. referral-based 3D instance segmentation. We propose a dense 3D grounding network ConcreteNet, featuring four novel stand-alone modules that aim to improve grounding performance for challenging repetitive instances, i.e. instances with distractors of the same semantic class. First, we introduce a bottom-up attentive fusion module that aims to disambiguate inter-instance relational cues, next, we construct a contrastive training scheme to induce separation in the latent space, we then resolve view-dependent utterances via a learned global camera token, and finally we employ multi-view ensembling to improve referred mask quality. ConcreteNet ranks \(1^{st}\) on the challenging ScanRefer online benchmark and has won the ICCV \(3^{rd}\) Workshop on Language for 3D Scenes “3D Object Localization” challenge. Our code is available at ouenal.github.io/concretenet/.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    Classifying each point yields a more robust solution compared to the localization of 8 corner points in complete free 3D space.

  2. 2.

    We believe that input camera positions are a reasonable assumption in indoor robotic applications and hope that this performance potential will motivate future research.

References

  1. Achlioptas, P., Abdelreheem, A., Xia, F., Elhoseiny, M., Guibas, L.: ReferIt3D: neural listeners for fine-grained 3D object identification in real-world scenes. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 422–440. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_25

    Chapter  Google Scholar 

  2. Cai, D., Zhao, L., Zhang, J., Sheng, L., Xu, D.: 3DJCG: a unified framework for joint dense captioning and visual grounding on 3D point clouds. In: CVPR (2022)

    Google Scholar 

  3. Chen, D.Z., Chang, A.X., Nießner, M.: ScanRefer: 3D object localization in RGB-D scans using natural language. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 202–221. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58565-5_13

    Chapter  Google Scholar 

  4. Chen, D.Z., Wu, Q., Nießner, M., Chang, A.X.: D3Net: a unified speaker-listener architecture for 3D dense captioning and visual grounding. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part XXXII, pp. 487–505. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19824-3_29

  5. Chen, J., Luo, W., Wei, X., Ma, L., Zhang, W.: HAM: hierarchical attention model with high performance for 3D visual grounding. arXiv preprint arXiv:2210.12513 (2022)

  6. Chen, Z., Gholami, A., Nießner, M., Chang, A.X.: Scan2cap: context-aware dense captioning in RGB-d scans. In: CVPR (2021)

    Google Scholar 

  7. Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR (2022)

    Google Scholar 

  8. Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nießner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: ICCV (2017)

    Google Scholar 

  9. Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)

  10. Feng, M., et al.: Free-form description guided 3D visual graph network for object grounding in point cloud. In: ICCV (2021)

    Google Scholar 

  11. Goyal, A., Yang, K., Yang, D., Deng, J.: Rel3D: a minimally contrastive benchmark for grounding spatial relations in 3D. In: NIPS (2020)

    Google Scholar 

  12. Guo, Z., et al.: Viewrefer: grasp the multi-view knowledge for 3d visual grounding. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 15372–15383 (2023)

    Google Scholar 

  13. He, T., Shen, C., Van Den Hengel, A.: Dyco3d: robust instance segmentation of 3d point clouds through dynamic convolution. In: CVPR (2021)

    Google Scholar 

  14. Huang, P.H., Lee, H.H., Chen, H.T., Liu, T.L.: Text-guided graph neural networks for referring 3D instance segmentation. In: AAAI (2021)

    Google Scholar 

  15. Huang, S., Chen, Y., Jia, J., Wang, L.: Multi-view transformer for 3D visual grounding. In: CVPR (2022)

    Google Scholar 

  16. Jain, A., Gkanatsios, N., Mediratta, I., Fragkiadaki, K.: Bottom up top down detection transformers for language grounding in images and point clouds. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part XXXVI, pp. 417–433. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-20059-5_24

  17. Jiang, L., Zhao, H., Shi, S., Liu, S., Fu, C.W., Jia, J.: Pointgroup: dual-set point grouping for 3d instance segmentation. In: CVPR (2020)

    Google Scholar 

  18. Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: Referitgame: referring to objects in photographs of natural scenes. In: EMNLP (2014)

    Google Scholar 

  19. Kong, C., Lin, D., Bansal, M., Urtasun, R., Fidler, S.: What are you talking about? text-to-image coreference. In: ICCV (2014)

    Google Scholar 

  20. Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)

  21. Luo, J., et al.:: 3D-SPS: Single-stage 3D visual grounding via referred point progressive selection. In: CVPR (2022)

    Google Scholar 

  22. Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: ICCV (2016)

    Google Scholar 

  23. Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP (2014)

    Google Scholar 

  24. Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: ICCV (2015)

    Google Scholar 

  25. Prabhudesai, M., Tung, H.Y.F., Javed, S.A., Sieb, M., Harley, A.W., Fragkiadaki, K.: Embodied language grounding with 3D visual feature representations. In: CVPR (2020)

    Google Scholar 

  26. Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)

    Google Scholar 

  27. Roh, J., Desingh, K., Farhadi, A., Fox, D.: LanguageRefer: spatial-language model for 3D visual grounding. In: CoRL (2022)

    Google Scholar 

  28. Rozenberszki, D., Litany, O., Dai, A.: Language-grounded indoor 3D semantic segmentation in the wild. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part XXXIII, pp. 125–141. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19827-4_8

  29. Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746–760. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33715-4_54

    Chapter  Google Scholar 

  30. Song, K., Tan, X., Qin, T., Lu, J., Liu, T.Y.: Mpnet: masked and permuted pre-training for language understanding. In: NIPS (2020)

    Google Scholar 

  31. Vu, T., Kim, K., Luu, T.M., Nguyen, X.T., Yoo, C.D.: Softgroup for 3d instance segmentation on 3d point clouds. In: CVPR (2022)

    Google Scholar 

  32. Wu, Y., Cheng, X., Zhang, R., Cheng, Z., Zhang, J.: Eda: explicit text-decoupling and dense alignment for 3d visual grounding. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 19231–19242 (2023)

    Google Scholar 

  33. Wu, Y., Shi, M., Du, S., Lu, H., Cao, Z., Zhong, W.: 3D instances as 1D kernels. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part XXIX, pp. 235–252. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19818-2_14

  34. Yang, Z., Zhang, S., Wang, L., Luo, J.: SAT: 2D semantics assisted training for 3D visual grounding. In: ICCV (2021)

    Google Scholar 

  35. Yuan, Z., et al.: InstanceRefer: cooperative holistic understanding for visual grounding on point clouds through instance multi-level contextual referring. In: ICCV (2021)

    Google Scholar 

  36. Zhang, P., et al.: Multi-scale vision Longformer: a new vision transformer for high-resolution image encoding. In: ICCV (2021)

    Google Scholar 

  37. Zhang, Y., Gong, Z., Chang, A.X.: Multi3drefer: grounding text description to multiple 3d objects. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 15225–15236 (2023)

    Google Scholar 

  38. Zhao, L., Cai, D., Sheng, L., Xu, D.: 3DVG-transformer: relation modeling for visual grounding on point clouds. In: ICCV (2021)

    Google Scholar 

Download references

Acknowledgments

This work is funded by Toyota Motor Europe via the research project TRACE-Zürich.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ozan Unal .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 9181 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Unal, O., Sakaridis, C., Saha, S., Van Gool, L. (2025). Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15134. Springer, Cham. https://doi.org/10.1007/978-3-031-73116-7_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-73116-7_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-73115-0

  • Online ISBN: 978-3-031-73116-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics